© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18132
    Prev
    Next
    INDEX
    Explanations

    between entities

    np_acts-logits-general · gemini-2.5-flash-lite

    relationships between multilingual terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    与其他
    0.56
    與
    0.52
    与
    0.50
    我和
    0.45
     與
    0.44
    和
    0.42
    他和
    0.41
    跟
    0.40
     पित
    0.40
    정과
    0.39
    POSITIVE LOGITS
    之間的
    0.54
     തമ്മ
    0.50
    后者
    0.48
     arasındaki
    0.48
     दरम्यान
    0.46
     посредством
    0.44
     latter
    0.44
    之間
    0.43
     vise
    0.42
    之间的
    0.41
    Activations Density 0.210%

    No Known Activations